@kosiakmd/artillery-mcp

Richer drop-in MCP server for Artillery 2.x — exposes the full artillery run and artillery run-fargate flag surface, parses raw text output (artillery-output.txt), returns every counter/rate/summary Artillery produces (not just http.*), and optionally adds a config-driven project launcher and counter-grouping for your custom counters.

Why another MCP server?

The upstream @jch1887/artillery-mcp-server was a solid start but missed several flags our team needed day-to-day. This package is a MIT-licensed fork with broader coverage. See Credits.

Quickstart for agents (Claude Code / Cursor)

# In your project root
npx @kosiakmd/artillery-mcp init

Scaffolds two files (skipped if they already exist, use --force to overwrite):

• .artillery-mcp.config.json — starter template with commented fields
• .ai/skills/artillery-mcp/SKILL.md — agent-oriented guidance (when to call which tool, common patterns, gotchas)

After editing the config with your real flows/paths, register the MCP in your agent and restart the session:

claude mcp add artillery-mcp -s user \
  -e ARTILLERY_WORKDIR="$PWD" \
  -e ARTILLERY_CLOUD_API_KEY=a9_... \
  -- npx -y @kosiakmd/artillery-mcp

Install / Quickstart (zero-config)

Runs out of the box — no config file needed. Works as an MCP server over stdio for Claude Code, Claude Desktop, Cursor, and any MCP-compatible client.

# Using npx (no install)
npx -y @kosiakmd/artillery-mcp

# Or install globally
npm install -g @kosiakmd/artillery-mcp
artillery-mcp

Claude Code / Cursor — register as an MCP server in your client config:

{
  "mcpServers": {
    "artillery-mcp": {
      "command": "npx",
      "args": ["-y", "@kosiakmd/artillery-mcp"],
      "env": {
        "ARTILLERY_WORKDIR": "/absolute/path/to/your/project",
        "ARTILLERY_CLOUD_API_KEY": "a9_..."
      }
    }
  }
}

Claude Code CLI:

claude mcp add artillery-mcp -s user \
  -e ARTILLERY_WORKDIR=/abs/path/to/project \
  -e ARTILLERY_CLOUD_API_KEY=a9_... \
  -- npx -y @kosiakmd/artillery-mcp

Prerequisites: Node.js ≥ 20; Artillery CLI on PATH (npm i -g artillery).

Docker

Multi-arch image — linux/amd64 and linux/arm64, Artillery CLI preinstalled. ~500 MB (Chromium/Playwright browsers skipped — see below). Published to both Docker Hub and GitHub Container Registry from the same build; identical digests.

# Docker Hub (discoverable via `docker search artillery-mcp`)
docker pull kosiakmd/artillery-mcp:latest

# GitHub Container Registry
docker pull ghcr.io/kosiakmd/artillery-mcp:latest

Run (mount your project as /workspace):

docker run -i --init --rm \
  -v "$PWD":/workspace \
  -e ARTILLERY_CLOUD_API_KEY="$ARTILLERY_CLOUD_API_KEY" \
  kosiakmd/artillery-mcp:latest

--init ensures the Node process gets reaped on stdin close. Mount /workspace read-write if you want save_config tools to persist to /workspace/saved-configs/; read-only is fine otherwise (the save-config family will simply return errors when called).

MCP client config (Claude Desktop / Cursor) — point the MCP at docker instead of npx:

{
  "mcpServers": {
    "artillery-mcp": {
      "command": "docker",
      "args": [
        "run", "-i", "--init", "--rm",
        "-v", "/absolute/path/to/your/project:/workspace",
        "-e", "ARTILLERY_CLOUD_API_KEY",
        "kosiakmd/artillery-mcp:latest"
      ],
      "env": { "ARTILLERY_CLOUD_API_KEY": "a9_..." }
    }
  }
}

Playwright engine? If you use engine: playwright in your Artillery scripts, extend the base image with Chromium:

FROM kosiakmd/artillery-mcp:latest
ENV PLAYWRIGHT_SKIP_BROWSER_DOWNLOAD=0
RUN apk add --no-cache chromium nss freetype harfbuzz ttf-freefont \
 && npm i -g @playwright/test \
 && npx playwright install chromium

Image tags:

• latest — most recent release
• v0.1.1, v0.1, v0 — pinned by semver (patch / minor / major)

Environment variables

18 base tools (no config needed)

Run tests

• run_test_from_file — full-flag artillery run wrapper (see flag surface above).
• run_test_inline — same but takes YAML text, writes to a tmp file.
• quick_test — artillery quick <url> with rate/count/duration/method/headers/body.
• run_fargate — artillery run-fargate with --region, --cluster, --cpu, --memory, --launch-type, --spot, --subnet-ids, --security-group-ids, --task-role-name, --task-ephemeral-storage, --container-dns-servers, --max-duration, --packages, --secret, --no-assign-public-ip + all run-shared flags.
• run_preset_test — smoke / baseline / soak / spike presets against a URL.
• run_saved_config — re-run a saved config by name.

Parse + inspect results

• parse_results — reads an Artillery JSON report; returns summary + allCounters + allRates + allSummaries + scenarios + metadata.
• read_artillery_output — reads a raw Artillery stdout dump (e.g. artillery-output.txt saved from CI), returns rawText (with tail-truncation), summaryBlock, counters, rates, metrics (nested percentiles).
• run_report — converts an existing JSON results file to HTML via artillery report. Use when you have JSON from CI artifacts and want shareable HTML without re-running.
• compare_results — diff two Artillery JSON results for regression detection.

Saved configs

• save_config / list_configs / get_config / delete_config — persistent named Artillery configs.

Interactive builder

• wizard_start / wizard_step / wizard_finalize — interactive test builder.

Meta

• list_capabilities — versions of Artillery/Node/this server, configured paths, limits.

Optional feature #1 — Project launcher (run_project_lt)

Activated when a .artillery-mcp.config.json file is discovered. Gives you one-liner invocations instead of writing full artillery run ... flag lists.

Discovery precedence:

1. ARTILLERY_MCP_CONFIG env var (absolute path)
2. Walk up from ARTILLERY_WORKDIR / cwd looking for .artillery-mcp.config.json
3. No config → this tool is not registered

Config (.artillery-mcp.config.json):

{
  "flows": {
    "browse": "tests/load/browse.yml",
    "buy": "tests/load/buy.yml",
    "combined": "tests/load/combined.yml"
  },
  "environments": ["local", "staging", "prod"],
  "defaultTags": { "repo": "my-app", "owner": "Platform" },
  "tagTemplates": ["type:{flow}", "env:{env}", "source:mcp"],
  "outputDir": "load-test-results"
}

Call:

{ "flow": "buy", "environment": "staging", "note": "canary v42" }

Effective command:

artillery run \
  --record \
  --name "buy-staging-2026-04-15T00-35-00-000Z" \
  --tags "repo:my-app,owner:Platform,type:buy,env:staging,source:mcp" \
  -e staging \
  --note "canary v42" \
  -o /abs/project/load-test-results/buy-staging-2026-04-15T00-35-00-000Z.json \
  /abs/project/tests/load/buy.yml

Optional fields:

• tagTemplates — {flow}, {env}, plus any caller-supplied templateVars (e.g. {round})
• outputDir — relative to project root; if missing, outputs land at project root
• defaultTags — merged before templates
• environments — if empty, any environment name is accepted

Override on the call side: name, note, extraTags, outputJson, reportHtml, variables, overrides, record: false, validateOnly, extraArgs, templateVars.

Optional feature #2 — Counter-group bucketing (counterBreakdown)